Body pose estimation

Abstract

Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and a method for detecting a pose of a user. The program and method include receiving a monocular image that includes a depiction of a body of a user; detecting a plurality of skeletal joints of the body depicted in the monocular image; and determining a pose represented by the body depicted in the monocular image based on the detected plurality of skeletal joints of the body. A pose of an avatar is modified to match the pose represented by the body depicted in the monocular image by adjusting a set of skeletal joints of a rig of an avatar based on the detected plurality of skeletal joints of the body; and the avatar having the modified pose that matches the pose represented by the body depicted in the monocular image is generated for display.

What is claimed is: 
     
       1. A method comprising:
 receiving a video of a first user; 
 determining that a predetermined set of skeletal joints of the first user are visible in the video; 
 adjusting portions of a first avatar that correspond to the predetermined set of skeletal joints of the first user that are visible in the video to represent a pose of the predetermined set of skeletal joints; 
 causing display of the video that simultaneously depicts the first user and the first avatar representing the pose of the predetermined set of skeletal joints; 
 during display of the video that simultaneously depicts the first user and the first avatar, detecting a condition for capturing a screenshot; 
 storing, as a screenshot, a frame of the video that simultaneously depicts the first user and the first avatar in response to detecting the condition during display of the video; 
 concurrently with displaying the screenshot that comprises the frame of the video that simultaneously depicts the first user and the first avatar. displaying a separate region comprising a blank space indicating that receipt of a corresponding screenshot from a second user is pending; and 
 receiving input from the first user that selects the blank space. 
 
     
     
       2. The method of  claim 1 , further comprising receiving input from the first user that selects the first avatar from a plurality of avatars. 
     
     
       3. The method of  claim 1 , wherein the condition comprises passage of a threshold period of time. 
     
     
       4. The method of  claim 1 , wherein the condition comprises receiving a spoken command from the user to capture the screenshot. 
     
     
       5. The method of  claim 1 , wherein the condition comprises maintaining a particular pose for a threshold period of time. 
     
     
       6. A system comprising:
 a processor configured to perform operations comprising: 
 receiving a video of a first user; 
 determining that a predetermined set of skeletal joints of the first user are visible in the video; 
 adjusting portions of a first avatar that correspond to the predetermined set of skeletal joints of the first user that are visible in the video to represent a pose of the predetermined set of skeletal joints; 
 causing display of the video that simultaneously depicts the first user and the first avatar representing the pose of the predetermined set of skeletal joints; 
 during display of the video that simultaneously depicts the first user and the first avatar, detecting a condition for capturing a screenshot; 
 storing, as a screenshot, a frame of the video that simultaneously depicts the first user and the first avatar in response to detecting the condition during display of the video; 
 concurrently with displaying the screenshot that comprises the frame of the video that simultaneously depicts the first user and the first avatar, displaying a separate region comprising a blank space indicating that receipt of a corresponding screenshot from a second user is pending; and 
 receiving input from the first user that selects the blank space. 
 
     
     
       7. The method of  claim 1 , further comprising:
 causing a list of recipients to be presented in response to receiving the input from the first user that selects the blank space. 
 
     
     
       8. The method of  claim 7 , further comprising:
 receiving input that selects a designated recipient from the list of recipients as a second user; and 
 transmitting the screenshot to the second user in response to receiving the input that selects the designated recipient. 
 
     
     
       9. The method of  claim 8 , further comprising:
 causing receiving of a video of the second user; 
 causing determining that less than a second predetermined set of skeletal joints of the second user are visible in the video; 
 causing adjusting of portions of a second avatar that correspond to the less than all skeletal joints of the second user that are visible in the video to represent a pose of the second user; 
 causing detecting a second condition for capturing a second screenshot; and 
 causing capturing of a second screenshot of the second user and the second avatar in response to detecting the second condition. 
 
     
     
       10. The method of  claim 9 , further comprising:
 causing automatically sending of the second screenshot to the first user; and 
 causing the second screenshot to be presented in place of the blank space to the first user. 
 
     
     
       11. The method of  claim 1 , further comprising:
 generating, for display, a plurality of identical avatars having a first set of different poses; and 
 detecting that the pose corresponds to a specified pose. 
 
     
     
       12. The method of  claim 11  further comprising, in response to detecting that the pose corresponds to the specified pose:
 modifying the first set of different poses of the plurality of avatars to have identical poses that match the pose of the first user; and 
 generating for display the plurality of avatars having the identical poses. 
 
     
     
       13. The method of  claim 12  further comprising animating modification of the first set of different poses of the plurality of avatars in the generated display. 
     
     
       14. The method of  claim 1 , further comprising receiving input from the first user that selects a blank space, the blank space indicating that receipt of an image comprising another screenshot from a second user is pending. 
     
     
       15. The system of  claim 6 , wherein the operations further comprise:
 generating, for display, a plurality of identical avatars having a first set of different poses: and 
 detecting that the pose corresponds to a specified pose. 
 
     
     
       16. The system of  claim 6 , wherein the operations further comprise receiving input from the first user that selects the first avatar from a plurality of avatars. 
     
     
       17. The system of  claim 6 , wherein the condition comprises passage of a threshold period of time. 
     
     
       18. The system of  claim 6 , wherein the condition comprises receiving a spoken command from the user to capture the screenshot. 
     
     
       19. The system of  claim 6 , wherein the condition comprises maintaining a particular pose for a threshold period of time. 
     
     
       20. A non-transitory machine-readable storage medium that includes instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
 receiving a video of a first user; 
 determining that a predetermined set of skeletal joints of the first user are visible in the video; 
 adjusting portions of a first avatar that correspond to the predetermined set of skeletal joints of the first user that are visible in the video to represent a pose of the predetermined set of skeletal joints; 
 causing display of the video that simultaneously depicts the first user and the first avatar representing the pose of the predetermined set of skeletal joints; 
 during display of the video that simultaneously depicts the first user and the first avatar, detecting a condition for capturing a screenshot; storing, as a screenshot, a frame of the video that simultaneously depicts the first user and the first avatar in response to detecting the condition during display of the video; 
 concurrently with displaying the screenshot that comprises the frame of the video that simultaneously depicts the first user and the first avatar, displaying a separate region comprising a blank space indicating that receipt of a corresponding screenshot from a second user is pending; and 
 receiving input from the first user that selects the blank space.